From the uDemy course on LLM engineering.
https://www.udemy.com/course/llm-engineering-master-ai-and-large-language-models
You can not select more than 25 topics
Topics must start with a letter or number, can include dashes ('-') and can be up to 35 characters long.
201 lines
5.9 KiB
201 lines
5.9 KiB
{ |
|
"cells": [ |
|
{ |
|
"cell_type": "markdown", |
|
"id": "fe12c203-e6a6-452c-a655-afb8a03a4ff5", |
|
"metadata": {}, |
|
"source": [ |
|
"# End of week 1 exercise\n", |
|
"\n", |
|
"To demonstrate your familiarity with OpenAI API, and also Ollama, build a tool that takes a technical question, \n", |
|
"and responds with an explanation. This is a tool that you will be able to use yourself during the course!" |
|
] |
|
}, |
|
{ |
|
"cell_type": "code", |
|
"execution_count": null, |
|
"id": "c1070317-3ed9-4659-abe3-828943230e03", |
|
"metadata": {}, |
|
"outputs": [], |
|
"source": [ |
|
"# imports\n", |
|
"import os\n", |
|
"from dotenv import load_dotenv\n", |
|
"\n", |
|
"from IPython.display import Markdown, display, update_display\n", |
|
"from openai import OpenAI" |
|
] |
|
}, |
|
{ |
|
"cell_type": "code", |
|
"execution_count": null, |
|
"id": "4a456906-915a-4bfd-bb9d-57e505c5093f", |
|
"metadata": {}, |
|
"outputs": [], |
|
"source": [ |
|
"# constants\n", |
|
"\n", |
|
"MODEL_GPT = 'gpt-4o-mini'\n", |
|
"MODEL_LLAMA = 'llama3.2'" |
|
] |
|
}, |
|
{ |
|
"cell_type": "code", |
|
"execution_count": null, |
|
"id": "a8d7923c-5f28-4c30-8556-342d7c8497c1", |
|
"metadata": {}, |
|
"outputs": [], |
|
"source": [ |
|
"# set up environment\n", |
|
"load_dotenv(override=True)\n", |
|
"api_key = os.getenv(\"OPENAI_API_KEY\")\n", |
|
"\n", |
|
"# set up clients\n", |
|
"openai = OpenAI()\n", |
|
"ollama = OpenAI(base_url=\"http://localhost:11434/v1\" , api_key=\"ollama\")\n", |
|
"\n", |
|
"# set up system prompt\n", |
|
"system_prompt = \"You are a coding tutor. If the user asks you a question, answer it to the point. If you are asked to create a code snippet, generate the code in Python and then explain it shortly.\"" |
|
] |
|
}, |
|
{ |
|
"cell_type": "code", |
|
"execution_count": 53, |
|
"id": "58f098cb-4b4e-4394-b0b5-29db88e9101c", |
|
"metadata": {}, |
|
"outputs": [], |
|
"source": [ |
|
"def send_request(user_prompt, model=MODEL_LLAMA, stream=False):\n", |
|
" message = [{\"role\": \"system\", \"content\": system_prompt}, {\"role\": \"user\", \"content\": user_prompt}]\n", |
|
" if model.startswith(\"gpt\"):\n", |
|
" model_client = openai\n", |
|
" else:\n", |
|
" model_client = ollama\n", |
|
"\n", |
|
" \n", |
|
" response = model_client.chat.completions.create(\n", |
|
" model=model,\n", |
|
" messages=message,\n", |
|
" stream=stream\n", |
|
" )\n", |
|
"\n", |
|
" if stream:\n", |
|
" streaming = \"\"\n", |
|
" display_handle = display(Markdown(\"\"), display_id=True)\n", |
|
" for chunk in response:\n", |
|
" streaming += chunk.choices[0].delta.content or ''\n", |
|
" streaming = streaming.replace(\"```\",\"\").replace(\"markdown\", \"\")\n", |
|
" update_display(Markdown(streaming), display_id=display_handle.display_id)\n", |
|
"\n", |
|
" else:\n", |
|
" return display(Markdown(response.choices[0].message.content))\n", |
|
"\n" |
|
] |
|
}, |
|
{ |
|
"cell_type": "code", |
|
"execution_count": 49, |
|
"id": "3f0d0137-52b0-47a8-81a8-11a90a010798", |
|
"metadata": {}, |
|
"outputs": [ |
|
{ |
|
"name": "stdin", |
|
"output_type": "stream", |
|
"text": [ |
|
" How can I display python code properly while streaming the answer from openai? Create a code snippet for this. The streaming should happen in the code canvas.\n" |
|
] |
|
} |
|
], |
|
"source": [ |
|
"# here is the question; type over this to ask something new\n", |
|
"question = input()" |
|
] |
|
}, |
|
{ |
|
"cell_type": "code", |
|
"execution_count": 48, |
|
"id": "2bc093fa-b2ff-47e9-8ea8-e41499385116", |
|
"metadata": {}, |
|
"outputs": [], |
|
"source": [ |
|
"# question = \"\"\"How can I display python code properly while streaming the answer from openai? Create a code snippet for this. The streaming should happen in the code canvas.\"\"\"" |
|
] |
|
}, |
|
{ |
|
"cell_type": "code", |
|
"execution_count": null, |
|
"id": "60ce7000-a4a5-4cce-a261-e75ef45063b4", |
|
"metadata": {}, |
|
"outputs": [], |
|
"source": [ |
|
"# Get gpt-4o-mini to answer, with streaming\n", |
|
"send_request(model=MODEL_GPT, user_prompt=question, stream=True)" |
|
] |
|
}, |
|
{ |
|
"cell_type": "code", |
|
"execution_count": 54, |
|
"id": "8f7c8ea8-4082-4ad0-8751-3301adcf6538", |
|
"metadata": {}, |
|
"outputs": [ |
|
{ |
|
"data": { |
|
"text/markdown": [ |
|
"To display Python code properly with OpenAI's chat interface, you'll need to use the `code` formatting in the response format provided by the API endpoint. \n", |
|
"\n", |
|
"Here's an example of how you can modify the API request URL to include the formatted code:\n", |
|
"\n", |
|
"```python\n", |
|
"import requests\n", |
|
"import json\n", |
|
"\n", |
|
"query = {\n", |
|
" \"text\": \"{\\n} # Python code here\\n}\"\n", |
|
"\n", |
|
"headers = {\n", |
|
" 'Content-Type': 'application/json'\n", |
|
"}\n", |
|
"\n", |
|
"response = requests.post('https://api.openai.com/v1/answers', data=json.dumps(query), headers=headers)\n", |
|
"\n", |
|
"answer = response.json()\n", |
|
"```\n", |
|
"\n", |
|
"However, the most convenient way to display the code is by using the `code` directive directly in your chat prompt. OpenAI will automatically format and highlight your code." |
|
], |
|
"text/plain": [ |
|
"<IPython.core.display.Markdown object>" |
|
] |
|
}, |
|
"metadata": {}, |
|
"output_type": "display_data" |
|
} |
|
], |
|
"source": [ |
|
"# Get Llama 3.2 to answer\n", |
|
"send_request(user_prompt=question)" |
|
] |
|
} |
|
], |
|
"metadata": { |
|
"kernelspec": { |
|
"display_name": "Python 3 (ipykernel)", |
|
"language": "python", |
|
"name": "python3" |
|
}, |
|
"language_info": { |
|
"codemirror_mode": { |
|
"name": "ipython", |
|
"version": 3 |
|
}, |
|
"file_extension": ".py", |
|
"mimetype": "text/x-python", |
|
"name": "python", |
|
"nbconvert_exporter": "python", |
|
"pygments_lexer": "ipython3", |
|
"version": "3.11.11" |
|
} |
|
}, |
|
"nbformat": 4, |
|
"nbformat_minor": 5 |
|
}
|
|
|